Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| io.github.digitalweb33333-creator/x402-solana digitalweb33333-creator/x402-solana x402 paid API tools for AI agents on Solana: crypto safety, market data, KYB/AML verification. | |
| digline digline/digline Read, measure and explain LLM eval runs of a digline suite. Cannot promote a baseline. | |
| Dike dikeai/plugins Grounded MENA legal search, reasoning, citation resolution, and citation-graph traversal. | |
| Stitch Wand dilshaus/stitchwand Design token tools for Google Stitch: convert, validate, diff, lint, generate, and export. | |
| Dim Hour dim-hour/dim-hour Search 19,000+ verified places to eat and drink across 24 cities, each with a 0-100 quality score. | |
| MedRates dimaosipa/medrates.fyi Search US hospital prices, compare costs, and find insurance-negotiated rates. | |
| Pointframe MCP Server dimitar-radenkov/pointframe Windows screenshots, OCR, and redacted screen recording for AI agents. No desktop app needed. | |
| Local Vector Search MCP dimonsmart/localvectorsearchmcp Local Markdown search, navigation and editing via MCP, with optional vector embeddings. | |
| NuGet API Inspector dimonsmart/nugetmcpserver Inspect NuGet package APIs, dependencies, metadata, and breaking changes across versions. | |
| io.github.DinanathDash/envault dinanathdash/envault Secure secret management with a Human-In-The-Loop (HITL) interceptor for agent mutations. | |
| io.github.DingDawg-dev/dingdawg-compliance dingdawg-dev/dingdawg-compliance EU AI Act + Colorado AI Act compliance scoring. 87/100 in 60 seconds. Free local scan. | |
| io.github.DingDawg-dev/dingdawg-finance-agent dingdawg-dev/dingdawg-finance-agent Financial analysis AI. Forecasting, audit prep, SOX/GAAP compliance. Accuracy compounds with use. | |
| io.github.DingDawg-dev/dingdawg-healthcare-agent dingdawg-dev/dingdawg-healthcare-agent HIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier. | |
| io.github.dingdawg/dingdawg-devops-agent dingdawg/dingdawg-agent-1 DevOps AI. Deploy checks, incident analysis, infra audit. Learns from past failures. | |
| io.github.dingdawg/dingdawg-compliance dingdawg/dingdawg-compliance EU AI Act + Colorado AI Act compliance scoring. 87/100 in 60 seconds. Free local scan. | |
| io.github.dingw1982/weather dingw1982/quickstart-resources An MCP server for weather information. | |
| keyshroud dinhkarate/keyshroud Agent-safe secrets (local encrypted vault or Vaultwarden): injected into commands, masked in output | |
| io.github.dinof777/mission-control dinof777/mission-control Read and write Mission Control state via MCP — projects, tasks, subtasks, templates, status updates. | |
| MockHero dinosaur24/mockhero Generate realistic relational test data — 156 field types, 22 locales, JSON/CSV/SQL, free previews. | |
| io.github.dinosaur24/nodehero dinosaur24/zapguard AI workflow error analysis for n8n, Make, Zapier, and 10+ platforms. | |
| Cokodo Agent dinwind/agent_protocol Serve .agent/ project context, references, and collaborations to MCP-compatible IDEs. | |
| click.picale/picale-mcp direccion360/picale-mcp-api Pícale desde Claude, ChatGPT o cualquier cliente MCP: marca, contenido, publicaciones y resultados. | |
| click.vivento365/vivento-mcp direccion360/vivento-mcp Vivento 365 (CRM inmobiliario) desde Claude, ChatGPT o cualquier cliente MCP: prospectos y citas. | |
| DirectIQ directiq/mcp Manage DirectIQ contacts, lists and tags, see campaign results, and send transactional email. | |
| DiscordServers discordservers/monorepo Search Discord server listings, and manage your own servers once you sign in. | |
| io.github.discover-dmc/paygentic discover-dmc/paygentic Pay-per-call APIs for AI agents: web scraping, DNS/email checks, classification, trading risk. | |
| DiskSpace AI diskspaceai/diskspace-ai Analyze a Mac's disk, explain each folder and clean what recreates itself, with 7-day undo. | |
| io.github.Disseveru/cogfall disseveru/cogfall-api On-demand human cognitive fallback & CAPTCHA solver for AI agents with x402 micropayments. | |
| Divblox MCP divblox-group/divblox-mcp Define requirements, plan tickets and tasks, and track delivery with your Divblox projects. | |
| io.github.dizzydes/0pi dizzydes/botbox Free, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data. | |
| US Building Permit Aggregator dizzyvinci/apify-foundry Pull recent building permits from 9 US cities in a unified schema from official open-data portals. | |
| Shopify Catalog Monitor dizzyvinci/apify-foundry Track price drops, stock-outs, restocks, and new/removed products across Shopify stores. | |
| io.github.djanacek/coverageshield djanacek/coverageshield Insurance coverage requirements, gap detection, and risk profiles for US businesses. | |
| io.github.djaxho/amorphous djaxho/amorphous-plugin A page people use together. Your own agent builds it. | |
| Slimlytics djedi/slimlytics Privacy-first cookieless web analytics with agent one-prompt setup via remote MCP OAuth. | |
| GLM MCP djerok/glm-mcp GLM (Zhipu/Z.ai) as a ~10x cheaper file-editing subagent for AI coding agents. | |
| Nexus Finance djtellado/nexus-finance-prod Nexus Finance API — compliance audit, VaR/RWA risk, market quotes and case management. | |
| Samotpravil MCP dkanster/samotpravil-mcp MCP server for Samotpravil API — docs, typed tools, Python SDK parity, safety flags. | |
| Charter Boats dkremsa/charter-boats-mcp Search 14,000+ charter boats with live prices, plus marinas, anchorages, routes and itineraries. | |
| io.github.dl-eigenart/agentshield-mcp dl-eigenart/agentshield-platform Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents. | |
| Perigee dlamarre-dev/perigee Positions, distances, mission facts and 3D views of objects orbiting the Earth, Moon, Mars and Sun. | |
| MCP Surface Lint dleibner/mcp-surface-lint Statically audits MCP tool surfaces for token cost, schema quality, and design issues. | |
| AI-SDLC Prompts dleon55/ai-sdlc-prompts 112 SDLC prompts (ES/EN) for AI coding agents, each with its operating contract. | |
| DLL Execution dllio/dll-execution-docs Free read-only Base Mainnet transaction Preflight and Verification; no signing or custody. | |
| io.github.dmcsite/vibemind dmcsite/vibemind-ableton Claude builds FL Studio and Ableton Live sessions: notes, presets, mixer, automation, measured mixes | |
| Akmon dmitrii-nino/akmon-claude-plugin Rewrite text so it reads naturally, or paraphrase it in a chosen style. Works in many languages. | |
| io.github.dmsnavin/grandline-mcp dmsnavin/luzomi-grandline Empirical maritime distances from real AIS tracks: 4 route variants, port lookup, bulk matrix | |
| Western Container Sales dmurashi/ai.westerncontainersales.com Shipping-container sale and rental pricing, availability, delivery, and product discovery. | |
| Barvinca MCP dmytro-yemelianov/raps-tools Inspect ACC administration data and run bounded, approval-gated bulk user workflows. | |
| io.github.dns-aid/dns-aid dns-aid/dns-aid-core Discover and publish AI agents via DNS using SVCB records (RFC 9460) |
22,501–22,550 of 50,909
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.